Metraipolis › archive › dc_b5de01347bf5

Depth Any Seen: Which Surfaces and How Far? — arXiv:2609.32027

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32027
License (as archived)
CC0-1.0
Archived
2026-10-07T20:59:47.726Z
SHA-256 of the archived text
a7574903ed5ae962d9efb027bf65792b0c6a3a1d9dbea520e9bbed2ecef53574
Stable URL of this page
https://metraipolis.com/documento/dc_b5de01347bf5

How to cite

Depth Any Seen: Which Surfaces and How Far? — arXiv:2609.32027 — arXiv (en), https://arxiv.org/abs/2609.32027 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5de01347bf5 (Metraipolis archive dc_b5de01347bf5, sha256 a7574903ed5ae962d9efb027bf65792b0c6a3a1d9dbea520e9bbed2ecef53574)
BibTeX
@misc{dcb5de01347bf5,
  title = {Depth Any Seen: Which Surfaces and How Far? — arXiv:2609.32027},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32027},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5de01347bf5; sha256 a7574903ed5ae962d9efb027bf65792b0c6a3a1d9dbea520e9bbed2ecef53574},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32027. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When several surfaces are visible along a ray, recovering visible 3D structure from one image requires jointly estimating their presence and metric depth. Depth Any Seen represents these surfaces as image-conditioned multi-Bernoulli depth sets, whose components each contribute one depth or remain absent. Its auxiliary-free Exact Multi-Bernoulli objective (ExactMB) learns depth and presence by marginalizing one-to-one assignments to complete, distinct targets. Our analysis shows that matching expected count can leave component-surface assignment unresolved. We extend real and synthetic layered-depth benchmarks to evaluate depth accuracy, recovered support, and overprediction. Compared to depth stacking, ExactMB reduces overprediction by a relative 88.2% on LD-Real and 80.5% on MD-3K while retaining most ordinal accuracy, with comparable conditional metric-depth error on LD-Syn. Further ablation studies show that ordered assignment improves depth-accurate recall and precision over marginalization, whereas the count-regularized configuration achieves higher deeper-rank precision than ordered assignment at lower recall. Our code will be publicly released.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Graphics (cs.GR); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.32027 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:02.207Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).